Event-based features for robotic vision

This paper introduces a new time oriented visual feature extraction method developed to take full advantage of an asynchronous event-based camera. Event-based asynchronous cameras encode visual information in an extremely optimal manner in term of redundancy reduction and energy consumption. These sensors open vast perspectives in the field of mobile robotics where responsiveness is one of the most important needed property. The presented technique, based on echo-state networks will be shown particularly suited for unsupervised features extraction in the context of high dynamic environments. Experimental results are presented, they show the method adequacy with the high data sparseness and temporal resolution of event-based acquisition. This allows features extraction at millisecond accuracy with a low computational cost.